def train(self, hparams=lib.get_default_hparams()):
"""Feeds the training data for training.
Args:
hparams: A namedtuple of hyperparameters. This function expects
.train_epochs: a Python integer with the number of passes over the
training dataset;
.learning_rate: a Python float forwarded to the optimizer;
.momentum: a Python float forwarded to the optimizer;
.batch_size: a Python integer, number of samples per training step.
Returns:
The tf.keras.callbacks.History object returned by tf.keras.Model.fit*().
"""
train_data_and_size = (self._gen_train_dataset(self.train_data,
hparams.batch_size),
self.train_data.size)
validation_data_and_size = (self._gen_valid_dataset(self.valid_data,
hparams.batch_size),
self.valid_data.size)
# Trains the models.
return lib.train_model(self.model, hparams, train_data_and_size,
validation_data_and_size)
def train(self, train_data, validation_data=None, hparams=None):
"""Feeds the training data for training.
Args:
train_data: Training data.
validation_data: Validation data. If None, skips validation process.
hparams: A namedtuple of hyperparameters. This function expects
.train_epochs: a Python integer with the number of passes over the
training dataset;
.learning_rate: a Python float forwarded to the optimizer;
.momentum: a Python float forwarded to the optimizer;
.batch_size: a Python integer, number of samples per training step.
Returns:
The tf.keras.callbacks.History object returned by tf.keras.Model.fit*().
"""
hparams = self._get_hparams_or_default(hparams)
train_ds = self._gen_dataset(train_data,
hparams.batch_size,
is_training=True)
train_data_and_size = (train_ds, train_data.size)
validation_ds = None
validation_size = 0
if validation_data is not None:
validation_ds = self._gen_dataset(validation_data,
hparams.batch_size,
is_training=False)
validation_size = validation_data.size
validation_data_and_size = (validation_ds, validation_size)
# Trains the models.
return lib.train_model(self.model, hparams, train_data_and_size,
validation_data_and_size)